Forecaster

DontUpdate

Categorical in XInsamplePred int insampleExogenous

Turns off updates, i.e., ensures that forecaster is only fit and never updated.

This is useful when comparing forecasters that update with forecasters that don’t, in a set-up where all forecasters’ update has update_params=True set.

Shorthand for UpdateEvery with default values.

Quickstart

python

from sktime.forecasting.stream import DontUpdate

estimator = DontUpdate(forecaster)

Parameters(1)

forecasteran sktime forecaster: the forecaster for which update is called with update_params=False always, i.e., never updates.

Examples

>>> from sktime.forecasting.trend import TrendForecaster
>>> from sktime.forecasting.stream import DontUpdate
>>> from sktime.datasets import load_airline
>>> y = load_airline ()
>>> y0 = y. iloc [: - 20 ]
>>> y1 = y. iloc [- 20: - 10 ]
>>> y2 = y. iloc [- 10:]
>>> inner_forecaster = TrendForecaster ()
>>> forecaster = DontUpdate (inner_forecaster)
>>> forecaster. fit (y0, fh = [1, 2, 3 ]) DontUpdate(
... )
>>> # predict etc could be called here
>>> # e.g., forecaster.predict()
>>> # first update, calls update with update_params=False
>>> forecaster. update (y1) DontUpdate(
... )
>>> # second update, calls update with update_params=False
>>> forecaster. update (y2) DontUpdate(
... )